43dfa28
1
2
3
4
5
6
7
8
9
10
11
12
13
14
{ "step": 700, "val_loss": 1.114107608795166, "mmlu_acc": 0.2822265625, "arc_easy_acc": 0.271484375, "model_config": { "sequence_len": 2048, "vocab_size": 65536, "n_layer": 20, "n_head": 10, "n_kv_head": 10, "n_embd": 1280 } }